1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
|
# Cloudflare V1
import re
import sys
import time
from copy import deepcopy
from collections import OrderedDict
# ------------------------------------------------------------------------------- #
try:
from HTMLParser import HTMLParser
except ImportError:
if sys.version_info >= (3, 4):
import html
else:
from html.parser import HTMLParser
try:
from urlparse import urlparse, urljoin
except ImportError:
from urllib.parse import urlparse, urljoin
# ------------------------------------------------------------------------------- #
from .exceptions import (
CloudflareCode1020,
CloudflareIUAMError,
CloudflareSolveError,
CloudflareChallengeError,
CloudflareCaptchaError,
CloudflareCaptchaProvider
)
# ------------------------------------------------------------------------------- #
from .captcha import Captcha
from .interpreters import JavaScriptInterpreter
# ------------------------------------------------------------------------------- #
class Cloudflare():
def __init__(self, cloudscraper):
self.cloudscraper = cloudscraper
# ------------------------------------------------------------------------------- #
# Unescape / decode html entities
# ------------------------------------------------------------------------------- #
@staticmethod
def unescape(html_text):
if sys.version_info >= (3, 0):
if sys.version_info >= (3, 4):
return html.unescape(html_text)
return HTMLParser().unescape(html_text)
return HTMLParser().unescape(html_text)
# ------------------------------------------------------------------------------- #
# check if the response contains a valid Cloudflare challenge
# ------------------------------------------------------------------------------- #
@staticmethod
def is_IUAM_Challenge(resp):
try:
return (
resp.headers.get('Server', '').startswith('cloudflare')
and resp.status_code in [429, 503]
and re.search(r'/cdn-cgi/images/trace/jsch/', resp.text, re.M | re.S)
and re.search(
r'''<form .*?="challenge-form" action="/\S+__cf_chl_f_tk=''',
resp.text,
re.M | re.S
)
)
except AttributeError:
pass
return False
# ------------------------------------------------------------------------------- #
# check if the response contains new Cloudflare challenge
# ------------------------------------------------------------------------------- #
def is_New_IUAM_Challenge(self, resp):
try:
return (
self.is_IUAM_Challenge(resp)
and re.search(
r'''cpo.src\s*=\s*['"]/cdn-cgi/challenge-platform/\S+orchestrate/jsch/v1''',
resp.text,
re.M | re.S
)
)
except AttributeError:
pass
return False
# ------------------------------------------------------------------------------- #
# check if the response contains a v2 hCaptcha Cloudflare challenge
# ------------------------------------------------------------------------------- #
def is_New_Captcha_Challenge(self, resp):
try:
return (
self.is_Captcha_Challenge(resp)
and re.search(
r'''cpo.src\s*=\s*['"]/cdn-cgi/challenge-platform/\S+orchestrate/(captcha|managed)/v1''',
resp.text,
re.M | re.S
)
)
except AttributeError:
pass
return False
# ------------------------------------------------------------------------------- #
# check if the response contains a Cloudflare hCaptcha challenge
# ------------------------------------------------------------------------------- #
@staticmethod
def is_Captcha_Challenge(resp):
try:
return (
resp.headers.get('Server', '').startswith('cloudflare')
and resp.status_code == 403
and re.search(r'/cdn-cgi/images/trace/(captcha|managed)/', resp.text, re.M | re.S)
and re.search(
r'''<form .*?="challenge-form" action="/\S+__cf_chl_f_tk=''',
resp.text,
re.M | re.S
)
)
except AttributeError:
pass
return False
# ------------------------------------------------------------------------------- #
# check if the response contains Firewall 1020 Error
# ------------------------------------------------------------------------------- #
@staticmethod
def is_Firewall_Blocked(resp):
try:
return (
resp.headers.get('Server', '').startswith('cloudflare')
and resp.status_code == 403
and re.search(
r'<span class="cf-error-code">1020</span>',
resp.text,
re.M | re.DOTALL
)
)
except AttributeError:
pass
return False
# ------------------------------------------------------------------------------- #
# Wrapper for is_Captcha_Challenge, is_IUAM_Challenge, is_Firewall_Blocked
# ------------------------------------------------------------------------------- #
def is_Challenge_Request(self, resp):
if self.is_Firewall_Blocked(resp):
self.cloudscraper.simpleException(
CloudflareCode1020,
'Cloudflare has blocked this request (Code 1020 Detected).'
)
if self.is_New_Captcha_Challenge(resp):
self.cloudscraper.simpleException(
CloudflareChallengeError,
'Detected a Cloudflare version 2 Captcha challenge, This feature is not available in the opensource (free) version.'
)
if self.is_New_IUAM_Challenge(resp):
self.cloudscraper.simpleException(
CloudflareChallengeError,
'Detected a Cloudflare version 2 challenge, This feature is not available in the opensource (free) version.'
)
if self.is_Captcha_Challenge(resp) or self.is_IUAM_Challenge(resp):
if self.cloudscraper.debug:
print('Detected a Cloudflare version 1 challenge.')
return True
return False
# ------------------------------------------------------------------------------- #
# Try to solve cloudflare javascript challenge.
# ------------------------------------------------------------------------------- #
def IUAM_Challenge_Response(self, body, url, interpreter):
try:
formPayload = re.search(
r'<form (?P<form>.*?="challenge-form" '
r'action="(?P<challengeUUID>.*?'
r'__cf_chl_f_tk=\S+)"(.*?)</form>)',
body,
re.M | re.DOTALL
).groupdict()
if not all(key in formPayload for key in ['form', 'challengeUUID']):
self.cloudscraper.simpleException(
CloudflareIUAMError,
"Cloudflare IUAM detected, unfortunately we can't extract the parameters correctly."
)
payload = OrderedDict()
for challengeParam in re.findall(r'^\s*<input\s(.*?)/>', formPayload['form'], re.M | re.S):
inputPayload = dict(re.findall(r'(\S+)="(\S+)"', challengeParam))
if inputPayload.get('name') in ['r', 'jschl_vc', 'pass']:
payload.update({inputPayload['name']: inputPayload['value']})
except AttributeError:
self.cloudscraper.simpleException(
CloudflareIUAMError,
"Cloudflare IUAM detected, unfortunately we can't extract the parameters correctly."
)
hostParsed = urlparse(url)
try:
payload['jschl_answer'] = JavaScriptInterpreter.dynamicImport(
interpreter
).solveChallenge(body, hostParsed.netloc)
except Exception as e:
self.cloudscraper.simpleException(
CloudflareIUAMError,
f"Unable to parse Cloudflare anti-bots page: {getattr(e, 'message', e)}"
)
return {
'url': f"{hostParsed.scheme}://{hostParsed.netloc}{self.unescape(formPayload['challengeUUID'])}",
'data': payload
}
# ------------------------------------------------------------------------------- #
# Try to solve the Captcha challenge via 3rd party.
# ------------------------------------------------------------------------------- #
def captcha_Challenge_Response(self, provider, provider_params, body, url):
try:
formPayload = re.search(
r'<form (?P<form>.*?="challenge-form" '
r'action="(?P<challengeUUID>.*?__cf_chl_captcha_tk__=\S+)"(.*?)</form>)',
body,
re.M | re.DOTALL
).groupdict()
if not all(key in formPayload for key in ['form', 'challengeUUID']):
self.cloudscraper.simpleException(
CloudflareCaptchaError,
"Cloudflare Captcha detected, unfortunately we can't extract the parameters correctly."
)
payload = OrderedDict(
re.findall(
r'(name="r"\svalue|data-ray|data-sitekey|name="cf_captcha_kind"\svalue)="(.*?)"',
formPayload['form']
)
)
captchaType = 'reCaptcha' if payload['name="cf_captcha_kind" value'] == 're' else 'hCaptcha'
except (AttributeError, KeyError):
self.cloudscraper.simpleException(
CloudflareCaptchaError,
"Cloudflare Captcha detected, unfortunately we can't extract the parameters correctly."
)
# ------------------------------------------------------------------------------- #
# Pass proxy parameter to provider to solve captcha.
# ------------------------------------------------------------------------------- #
if self.cloudscraper.proxies and self.cloudscraper.proxies != self.cloudscraper.captcha.get('proxy'):
self.cloudscraper.captcha['proxy'] = self.proxies
# ------------------------------------------------------------------------------- #
# Pass User-Agent if provider supports it to solve captcha.
# ------------------------------------------------------------------------------- #
self.cloudscraper.captcha['User-Agent'] = self.cloudscraper.headers['User-Agent']
# ------------------------------------------------------------------------------- #
# Submit job to provider to request captcha solve.
# ------------------------------------------------------------------------------- #
captchaResponse = Captcha.dynamicImport(
provider.lower()
).solveCaptcha(
captchaType,
url,
payload['data-sitekey'],
provider_params
)
# ------------------------------------------------------------------------------- #
# Parse and handle the response of solved captcha.
# ------------------------------------------------------------------------------- #
dataPayload = OrderedDict([
('r', payload.get('name="r" value', '')),
('cf_captcha_kind', payload['name="cf_captcha_kind" value']),
('id', payload.get('data-ray')),
('g-recaptcha-response', captchaResponse)
])
if captchaType == 'hCaptcha':
dataPayload.update({'h-captcha-response': captchaResponse})
hostParsed = urlparse(url)
return {
'url': f"{hostParsed.scheme}://{hostParsed.netloc}{self.unescape(formPayload['challengeUUID'])}",
'data': dataPayload
}
# ------------------------------------------------------------------------------- #
# Attempt to handle and send the challenge response back to cloudflare
# ------------------------------------------------------------------------------- #
def Challenge_Response(self, resp, **kwargs):
if self.is_Captcha_Challenge(resp):
# ------------------------------------------------------------------------------- #
# double down on the request as some websites are only checking
# if cfuid is populated before issuing Captcha.
# ------------------------------------------------------------------------------- #
if self.cloudscraper.doubleDown:
resp = self.cloudscraper.decodeBrotli(
self.cloudscraper.perform_request(resp.request.method, resp.url, **kwargs)
)
if not self.is_Captcha_Challenge(resp):
return resp
# ------------------------------------------------------------------------------- #
# if no captcha provider raise a runtime error.
# ------------------------------------------------------------------------------- #
if (
not self.cloudscraper.captcha
or not isinstance(self.cloudscraper.captcha, dict)
or not self.cloudscraper.captcha.get('provider')
):
self.cloudscraper.simpleException(
CloudflareCaptchaProvider,
"Cloudflare Captcha detected, unfortunately you haven't loaded an anti Captcha provider "
"correctly via the 'captcha' parameter."
)
# ------------------------------------------------------------------------------- #
# if provider is return_response, return the response without doing anything.
# ------------------------------------------------------------------------------- #
if self.cloudscraper.captcha.get('provider') == 'return_response':
return resp
# ------------------------------------------------------------------------------- #
# Submit request to parser wrapper to solve captcha
# ------------------------------------------------------------------------------- #
submit_url = self.captcha_Challenge_Response(
self.cloudscraper.captcha.get('provider'),
self.cloudscraper.captcha,
resp.text,
resp.url
)
else:
# ------------------------------------------------------------------------------- #
# Cloudflare requires a delay before solving the challenge
# ------------------------------------------------------------------------------- #
if not self.cloudscraper.delay:
try:
delay = float(
re.search(
r'submit\(\);\r?\n\s*},\s*([0-9]+)',
resp.text
).group(1)
) / float(1000)
if isinstance(delay, (int, float)):
self.cloudscraper.delay = delay
except (AttributeError, ValueError):
self.cloudscraper.simpleException(
CloudflareIUAMError,
"Cloudflare IUAM possibility malformed, issue extracing delay value."
)
time.sleep(self.cloudscraper.delay)
# ------------------------------------------------------------------------------- #
submit_url = self.IUAM_Challenge_Response(
resp.text,
resp.url,
self.cloudscraper.interpreter
)
# ------------------------------------------------------------------------------- #
# Send the Challenge Response back to Cloudflare
# ------------------------------------------------------------------------------- #
if submit_url:
def updateAttr(obj, name, newValue):
try:
obj[name].update(newValue)
return obj[name]
except (AttributeError, KeyError):
obj[name] = {}
obj[name].update(newValue)
return obj[name]
cloudflare_kwargs = deepcopy(kwargs)
cloudflare_kwargs['allow_redirects'] = False
cloudflare_kwargs['data'] = updateAttr(
cloudflare_kwargs,
'data',
submit_url['data']
)
urlParsed = urlparse(resp.url)
cloudflare_kwargs['headers'] = updateAttr(
cloudflare_kwargs,
'headers',
{
'Origin': f'{urlParsed.scheme}://{urlParsed.netloc}',
'Referer': resp.url
}
)
challengeSubmitResponse = self.cloudscraper.request(
'POST',
submit_url['url'],
**cloudflare_kwargs
)
if challengeSubmitResponse.status_code == 400:
self.cloudscraper.simpleException(
CloudflareSolveError,
'Invalid challenge answer detected, Cloudflare broken?'
)
# ------------------------------------------------------------------------------- #
# Return response if Cloudflare is doing content pass through instead of 3xx
# else request with redirect URL also handle protocol scheme change http -> https
# ------------------------------------------------------------------------------- #
if not challengeSubmitResponse.is_redirect:
return challengeSubmitResponse
else:
cloudflare_kwargs = deepcopy(kwargs)
cloudflare_kwargs['headers'] = updateAttr(
cloudflare_kwargs,
'headers',
{'Referer': challengeSubmitResponse.url}
)
if not urlparse(challengeSubmitResponse.headers['Location']).netloc:
redirect_location = urljoin(
challengeSubmitResponse.url,
challengeSubmitResponse.headers['Location']
)
else:
redirect_location = challengeSubmitResponse.headers['Location']
return self.cloudscraper.request(
resp.request.method,
redirect_location,
**cloudflare_kwargs
)
# ------------------------------------------------------------------------------- #
# We shouldn't be here...
# Re-request the original query and/or process again....
# ------------------------------------------------------------------------------- #
return self.cloudscraper.request(resp.request.method, resp.url, **kwargs)
# ------------------------------------------------------------------------------- #
|
